© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1990
    Prev
    Next
    INDEX
    Explanations

    code terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èħ§
    -0.21
    AVED
    -0.21
    č↵↵
    -0.20
    aved
    -0.20
     QTableWidgetItem
    -0.19
     NSLocalizedString
    -0.18
    moz
    -0.18
    éŀ²
    -0.17
    .MinValue
    -0.17
    æĹ¥æĻļéĹ´
    -0.17
    POSITIVE LOGITS
    .IsNullOr
    0.23
    ibraltar
    0.22
    (jq
    0.22
    ecimal
    0.20
    insic
    0.20
    /swagger
    0.20
    .promise
    0.19
    shed
    0.19
    PointerException
    0.19
    @update
    0.19
    Activations Density 0.007%

    No Known Activations